Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1678. Min Range: -5.1678
Max Act: 5.1678. Min Act: -0.1700
Data Index: 2744398 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1678. Min Range: -5.1678
Max Act: 5.1053. Min Act: -0.1700
Data Index: 7196546 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1678. Min Range: -5.1678
Max Act: 5.0428. Min Act: -0.1700
Data Index: 2060918 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9803. Min Act: -0.1700
Data Index: 1455399 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9803. Min Act: -0.1700
Data Index: 1657690 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9491. Min Act: -0.1700
Data Index: 1485500 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9491. Min Act: -0.1700
Data Index: 3661994 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9491. Min Act: -0.1700
Data Index: 7517029 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9178. Min Act: -0.1700
Data Index: 2607094 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.9178. Min Act: -0.1700
Data Index: 8626092 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.8866. Min Act: -0.1700
Data Index: 8010134 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.8866. Min Act: -0.1700
Data Index: 8363131 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.8866. Min Act: -0.1700
Data Index: 6141617 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.8866. Min Act: -0.1700
Data Index: 4868066 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.8553. Min Act: -0.1700
Data Index: 631768 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.7928. Min Act: -0.1700
Data Index: 360096 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.7928. Min Act: -0.1700
Data Index: 5371362 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.7928. Min Act: -0.1700
Data Index: 3109373 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.7928. Min Act: -0.1700
Data Index: 5819964 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1678. Min Range: -5.1678
Max Act: 4.7616. Min Act: -0.1700
Data Index: 2437004 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19